home / mcp / manim mcp server

Manim MCP Server

Executes Manim scripts and returns rendered animation videos via an MCP server for easy integration.

Installation
Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "abhiemj-manim-mcp-server": {
      "command": "/absolute/path/to/python",
      "args": [
        "/absolute/path/to/manim-mcp-server/src/manim_server.py"
      ],
      "env": {
        "MANIM_EXECUTABLE": "/Users/[Your_username]/anaconda3/envs/manim2/Scripts/manim.exe"
      }
    }
  }
}

You can render Manim animations on demand using this MCP server. You send Manim script content to the server, and it executes the script to produce a video file that you can access from the server’s media folder. It also cleans up temporary files after execution and lets you configure the environment for flexible, portable use.

How to use

To use the Manim MCP Server, you connect an MCP client to the server endpoint. You provide a Manim script or module, and the server runs Manim to render the animation. The resulting video is saved in a visible media folder so you can retrieve it. If you want to run multiple animations in sequence or clean up intermediates, you can trigger additional requests and rely on the server to manage temporary files.

How to install

Prerequisites you need before installing the server:

Python 3.8+

Manim (Community Version)

MCP

# Install Manim
pip install manim

# Install MCP
pip install mcp

# Clone the server repository
git clone https://github.com/abhiemj/manim-mcp-server.git
cd manim-mcp-server

Available tools

manim_runner

Executes a Manim Python script and renders the animation to a video file.

temp_cleanup

Cleans up temporary files after execution to keep the workspace tidy.

output_store

Saves rendered videos to a visible media folder for easy retrieval.

env_config

Supports configurable environment variables to customize execution, such as the MANIM_EXECUTABLE path.